CBCT correction using a cycle-consistent generative adversarial network and unpaired training to enable photon and proton dose calculation
CBCT correction using a cycle-consistent generative adversarial network and unpaired training to enable photon and proton dose calculation
复制标题
DOI：
10.1088/1361-6560/ab4d8c
复制
发表时间：
2019-11-01
影响因子：
3.5
通讯作者：
van den Berg, Cornelis A. T.
中科院分区：
文献类型：
--
作者：
Kurz, Christopher;Maspero, Matteo;van den Berg, Cornelis A. T.
在存在的分数解剖变化，临床效益预期从图像引导的适应性放疗。目前，锥形束CT （cone-beam CT， CBCT）成像多用于预处理成像中的位置验证。由于各种伪影，图像质量通常不足以用于光子或质子剂量计算，因此需要精确的CBCT校正，这可能由深度学习技术提供。本研究旨在探讨利用周期一致生成对抗网络（cycleGAN）进行非配对训练的前列腺CBCT校正的可行性。纳入33例患者。训练该网络将未校正的原始CBCT图像（CBCTorg）转换为规划的CT等效图像（CBCTcycleGAN）。通过与先前验证的CBCT校正技术（CBCTcor）进行比较来确定HU的准确性。对体积调制电弧光子治疗（VMAT）和相反的单场均匀剂量（OSFUD）质子计划进行剂量学精度推断，在CBCTcor上进行优化，并在CBCTcycleGAN上重新计算。单侧SFUD质子计划用于评估质子范围的准确性。CBCTcycleGAN相对于CBCTcor的平均HU误差从CBCTorg的24 HU减小到？？6。VMAT的剂量计算精度高，2%/1%剂量差标准的平均通过率为100%/89%。对于质子OSFUD计划，2%剂量差标准的平均通过率为80%。使用(2%,2？Mm) γ标准，通过率为96%。在所有分析的SFUD剖面中，93%的范围一致性优于33.5 mm。CBCT校正时间从6?10？CBCTcor的min到CBCTcycleGAN的10s。我们的研究证明了利用cycleGAN进行CBCT校正的可行性，实现了VMAT的高剂量计算精度。对于质子治疗，可能需要进一步的改进。由于非配对训练，该方法不依赖于解剖学上一致的训练数据或可能不准确的变形图像配准。CBCT校正的大幅加速使该方法对适应性放疗特别感兴趣。
In presence of inter-fractional anatomical changes, clinical benefits are anticipated from image-guided adaptive radiotherapy. Nowadays, cone-beam CT (CBCT) imaging is mostly utilized during pre-treatment imaging for position verification. Due to various artifacts, image quality is typically not sufficient for photon or proton dose calculation, thus demanding accurate CBCT correction, as potentially provided by deep learning techniques. This work aimed at investigating the feasibility of utilizing a cycle-consistent generative adversarial network (cycleGAN) for prostate CBCT correction using unpaired training. Thirty-three patients were included. The network was trained to translate uncorrected, original CBCT images (CBCTorg) into planning CT equivalent images (CBCTcycleGAN). HU accuracy was determined by comparison to a previously validated CBCT correction technique (CBCTcor). Dosimetric accuracy was inferred for volumetric-modulated arc photon therapy (VMAT) and opposing single-field uniform dose (OSFUD) proton plans, optimized on CBCTcor and recalculated on CBCTcycleGAN. Single-sided SFUD proton plans were utilized to assess proton range accuracy. The mean HU error of CBCTcycleGAN with respect to CBCTcor decreased from 24 HU for CBCTorg to???6 HU. Dose calculation accuracy was high for VMAT, with average pass-rates of 100%/89% for a 2%/1% dose difference criterion. For proton OSFUD plans, the average pass-rate for a 2% dose difference criterion was 80%. Using a (2%, 2?mm) gamma criterion, the pass-rate was 96%. 93% of all analyzed SFUD profiles had a range agreement better than 3?mm. CBCT correction time was reduced from 6?10?min for CBCTcor to 10 s for CBCTcycleGAN. Our study demonstrated the feasibility of utilizing a cycleGAN for CBCT correction, achieving high dose calculation accuracy for VMAT. For proton therapy, further improvements may be required. Due to unpaired training, the approach does not rely on anatomically consistent training data or potentially inaccurate deformable image registration. The substantial speed-up for CBCT correction renders the method particularly interesting for adaptive radiotherapy.